AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

CoMA-SLAM: Collaborative Multi-Agent Gaussian SLAM with Geometric Consistency

Lin Chen, Yongxin Su, Jvboxi Wang, Pengcheng Han, Zhenyu Xia, Shuhui Bu, Kun Li, Boni Hu, Shengqi Meng, Guangming Wang

AAAI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace 3D Gaussians with 2D Gaussian surfels (ablation)CoMA-SLAM · ReplicaMultiagent Office-0ATE RMSE (cm): 0.24 -> 0.10Improved
replace 3D Gaussians with 2D Gaussian surfels (ablation)CoMA-SLAM · ReplicaMultiagent Office-0PSNR (dB): 42.21 -> 42.77No clear effect
add surface fitting initialization instead of random (ablation)CoMA-SLAM · ReplicaMultiagent Office-0ATE RMSE (cm): 0.18 -> 0.10Improved
add surface fitting initialization instead of random (ablation)CoMA-SLAM · ReplicaMultiagent Office-0PSNR (dB): 41.40 -> 42.77Improved
add loop closure (ablation)CoMA-SLAM · ReplicaMultiagent Office-0 (per-agent eval)ATE RMSE (cm): 0.21 -> 0.10Improved
add loop closure (ablation)CoMA-SLAM · ReplicaMultiagent Office-0PSNR (dB): 42.73 -> 42.77No clear effect
add adaptive Gaussian growth (ablation)CoMA-SLAM · ReplicaMultiagent Office-0Gaussian count (M): 1.05M -> 0.71MImproved
add adaptive Gaussian growth (ablation)CoMA-SLAM · ReplicaMultiagent Office-0ATE RMSE (cm): 0.10 -> 0.10No clear effect
use distributed design instead of centralized serverCoMA-SLAM vs MAGiC-SLAM · ReplicaMultiagent Office-0communication per frame: 1.7MB -> 2.2KBImproved
use CoMA-SLAM instead of MAGiC-SLAMmulti-agent Gaussian SLAM · ReplicaMultiagent Apt-1ATE RMSE (cm): 0.26 -> 0.27No clear effect
use CoMA-SLAM instead of MAGiC-SLAM on tracking per-frame costmulti-agent Gaussian SLAM · ReplicaMultiagent Office-0tracking time per frame (s): 0.10s -> 0.16sHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy